Unsupervisedcom · nhorton · Jan 12, 2026 · Jan 12, 2026 · Jan 12, 2026 · Jan 12, 2026
diff --git a/.claude/commands/deepwork_jobs.define.md b/.claude/commands/deepwork_jobs.define.md
@@ -17,7 +17,7 @@ hooks:
             4. **Concise Summary**: Is the summary under 200 characters and descriptive?
             5. **Rich Description**: Does the description provide enough context for future refinement?
             6. **Valid Schema**: Does the job.yml follow the required schema (name, version, summary, steps)?
-            7. **File Created**: Has the job.yml file been created in `deepwork/[job_name]/job.yml`?
+            7. **File Created**: Has the job.yml file been created in `.deepwork/jobs/[job_name]/job.yml`?
 
             If ANY criterion is not met, continue working to address it.
             If ALL criteria are satisfied, include `<promise>QUALITY_COMPLETE</promise>` in your response.
@@ -192,9 +192,9 @@ stop_hooks:
 
 Only after you have complete understanding, create the `job.yml` file:
 
-**File Location**: `deepwork/[job_name]/job.yml`
+**File Location**: `.deepwork/jobs/[job_name]/job.yml`
 
-(Where `[job_name]` is the name of the NEW job you're creating, e.g., `deepwork/competitive_research/job.yml`)
+(Where `[job_name]` is the name of the NEW job you're creating, e.g., `.deepwork/jobs/competitive_research/job.yml`)
 
 **Format**:
 ```yaml
@@ -357,12 +357,12 @@ User: Yes, that's perfect!
 
 Claude: Great! Creating the job.yml specification now...
 
-[Creates deepwork/competitive_research/job.yml with the complete spec]
+[Creates .deepwork/jobs/competitive_research/job.yml with the complete spec]
 
 ✓ Job specification created!
 
 **File created:**
-- deepwork/competitive_research/job.yml
+- .deepwork/jobs/competitive_research/job.yml
 
 **Next step:**
 Run `/deepwork_jobs.implement` to generate the instruction files for each step based on this specification.
@@ -396,9 +396,9 @@ Before creating the job.yml, ensure:
 
 ### job.yml
 
-The complete YAML specification file (example shown in Step 4 above).
+The complete YAML specification file (example shown in Step 5 above).
 
-**Location**: `deepwork/[job_name]/job.yml`
+**Location**: `.deepwork/jobs/[job_name]/job.yml`
 
 (Where `[job_name]` is the name of the new job being created)
 
@@ -466,7 +466,7 @@ Verify the job.yml output meets ALL quality criteria before completing:
 4. **Concise Summary**: Is the summary under 200 characters and descriptive?
 5. **Rich Description**: Does the description provide enough context for future refinement?
 6. **Valid Schema**: Does the job.yml follow the required schema (name, version, summary, steps)?
-7. **File Created**: Has the job.yml file been created in `deepwork/[job_name]/job.yml`?
+7. **File Created**: Has the job.yml file been created in `.deepwork/jobs/[job_name]/job.yml`?
 
 If ANY criterion is not met, continue working to address it.
 If ALL criteria are satisfied, include `<promise>QUALITY_COMPLETE</promise>` in your response.

diff --git a/.claude/commands/deepwork_jobs.implement.md b/.claude/commands/deepwork_jobs.implement.md
@@ -80,7 +80,7 @@ Read the `job.yml` specification file and create all the necessary files to make
 ### Step 1: Read and Validate the Specification
 
 1. **Locate the job.yml file**
-   - Read `deepwork/[job_name]/job.yml` from the define step (Where `[job_name]` is the name of the new job that was created in the define step)
+   - Read `.deepwork/jobs/[job_name]/job.yml` from the define step (Where `[job_name]` is the name of the new job that was created in the define step)
    - Parse the YAML content
 
 2. **Validate the specification**
@@ -213,13 +213,9 @@ If a step in the job.yml has `stop_hooks` defined, the generated instruction fil
 
 This alignment ensures the AI agent knows exactly what will be validated and can self-check before completing.
 
-### Step 4: Copy job.yml to Job Directory
+### Step 4: Verify job.yml Location
 
-Copy the validated `job.yml` from the work directory to `.deepwork/jobs/[job_name]/job.yml`:
-
-```bash
-cp deepwork/[job_name]/job.yml .deepwork/jobs/[job_name]/job.yml
-```
+Verify that `job.yml` is in the correct location at `.deepwork/jobs/[job_name]/job.yml`. The define step should have created it there. If for some reason it's not there, you may need to create or move it.
 
 ### Step 5: Sync Commands
 

diff --git a/.deepwork/jobs/deepwork_jobs/job.yml b/.deepwork/jobs/deepwork_jobs/job.yml
@@ -43,7 +43,7 @@ steps:
           4. **Concise Summary**: Is the summary under 200 characters and descriptive?
           5. **Rich Description**: Does the description provide enough context for future refinement?
           6. **Valid Schema**: Does the job.yml follow the required schema (name, version, summary, steps)?
-          7. **File Created**: Has the job.yml file been created in `deepwork/[job_name]/job.yml`?
+          7. **File Created**: Has the job.yml file been created in `.deepwork/jobs/[job_name]/job.yml`?
 
           If ANY criterion is not met, continue working to address it.
           If ALL criteria are satisfied, include `<promise>QUALITY_COMPLETE</promise>` in your response.

diff --git a/.deepwork/jobs/deepwork_jobs/steps/define.md b/.deepwork/jobs/deepwork_jobs/steps/define.md
@@ -133,9 +133,9 @@ stop_hooks:
 
 Only after you have complete understanding, create the `job.yml` file:
 
-**File Location**: `deepwork/[job_name]/job.yml`
+**File Location**: `.deepwork/jobs/[job_name]/job.yml`
 
-(Where `[job_name]` is the name of the NEW job you're creating, e.g., `deepwork/competitive_research/job.yml`)
+(Where `[job_name]` is the name of the NEW job you're creating, e.g., `.deepwork/jobs/competitive_research/job.yml`)
 
 **Format**:
 ```yaml
@@ -298,12 +298,12 @@ User: Yes, that's perfect!
 
 Claude: Great! Creating the job.yml specification now...
 
-[Creates deepwork/competitive_research/job.yml with the complete spec]
+[Creates .deepwork/jobs/competitive_research/job.yml with the complete spec]
 
 ✓ Job specification created!
 
 **File created:**
-- deepwork/competitive_research/job.yml
+- .deepwork/jobs/competitive_research/job.yml
 
 **Next step:**
 Run `/deepwork_jobs.implement` to generate the instruction files for each step based on this specification.
@@ -337,9 +337,9 @@ Before creating the job.yml, ensure:
 
 ### job.yml
 
-The complete YAML specification file (example shown in Step 4 above).
+The complete YAML specification file (example shown in Step 5 above).
 
-**Location**: `deepwork/[job_name]/job.yml`
+**Location**: `.deepwork/jobs/[job_name]/job.yml`
 
 (Where `[job_name]` is the name of the new job being created)
 

diff --git a/.deepwork/jobs/deepwork_jobs/steps/implement.md b/.deepwork/jobs/deepwork_jobs/steps/implement.md
@@ -11,7 +11,7 @@ Read the `job.yml` specification file and create all the necessary files to make
 ### Step 1: Read and Validate the Specification
 
 1. **Locate the job.yml file**
-   - Read `deepwork/[job_name]/job.yml` from the define step (Where `[job_name]` is the name of the new job that was created in the define step)
+   - Read `.deepwork/jobs/[job_name]/job.yml` from the define step (Where `[job_name]` is the name of the new job that was created in the define step)
    - Parse the YAML content
 
 2. **Validate the specification**
@@ -144,13 +144,9 @@ If a step in the job.yml has `stop_hooks` defined, the generated instruction fil
 
 This alignment ensures the AI agent knows exactly what will be validated and can self-check before completing.
 
-### Step 4: Copy job.yml to Job Directory
+### Step 4: Verify job.yml Location
 
-Copy the validated `job.yml` from the work directory to `.deepwork/jobs/[job_name]/job.yml`:
-
-```bash
-cp deepwork/[job_name]/job.yml .deepwork/jobs/[job_name]/job.yml
-```
+Verify that `job.yml` is in the correct location at `.deepwork/jobs/[job_name]/job.yml`. The define step should have created it there. If for some reason it's not there, you may need to create or move it.
 
 ### Step 5: Sync Commands
 

diff --git a/.github/workflows/validate.yml b/.github/workflows/validate.yml
@@ -4,18 +4,12 @@ on:
   pull_request:
     branches: ["*"]
 
-permissions:
-  contents: write
-
 jobs:
-  format:
+  tests:
     runs-on: ubuntu-latest
 
     steps:
       - uses: actions/checkout@v4
-        with:
-          ref: ${{ github.head_ref }}
-          token: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Install uv
         uses: astral-sh/setup-uv@v4
@@ -30,56 +24,10 @@ jobs:
       - name: Install dependencies
         run: uv sync --extra dev
 
-      - name: Run ruff formatting
-        run: uv run ruff format src/ tests/
-
-      - name: Run ruff linting with auto-fix
-        run: uv run ruff check --fix src/ tests/
-
-      - name: Re-run formatting after auto-fix
-        run: uv run ruff format src/ tests/
-
-      - name: Verify all issues are fixed
+      - name: Check formatting (ruff)
         run: |
-          uv run ruff check src/ tests/
           uv run ruff format --check src/ tests/
-
-      - name: Check for changes
-        id: check_changes
-        run: |
-          if [[ -n "$(git status --porcelain)" ]]; then
-            echo "has_changes=true" >> $GITHUB_OUTPUT
-          else
-            echo "has_changes=false" >> $GITHUB_OUTPUT
-          fi
-
-      - name: Commit and push formatting changes
-        if: steps.check_changes.outputs.has_changes == 'true'
-        run: |
-          git config --local user.email "github-actions[bot]@users.noreply.github.com"
-          git config --local user.name "github-actions[bot]"
-          git add -A
-          git commit -m "style: auto-format code with ruff"
-          git push
-
-  tests:
-    runs-on: ubuntu-latest
-
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Install uv
-        uses: astral-sh/setup-uv@v4
-        with:
-          version: "latest"
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.11"
-
-      - name: Install dependencies
-        run: uv sync --extra dev
+          uv run ruff check src/ tests/
 
       - name: Run tests
         run: uv run pytest tests/ -v
diff --git a/README.md b/README.md
@@ -4,21 +4,6 @@
 
 DeepWork is a tool for defining and executing multi-step workflows with AI coding assistants like Claude Code, Google Gemini, and GitHub Copilot. It enables you to decompose complex tasks into manageable steps, with clear inputs, outputs, and dependencies.
 
-## Status: Phase 1 MVP Complete ✅
-
-**Version**: 0.1.0
-**Test Coverage**: 166 tests passing
-
-### What's Implemented
-
-- ✅ Job definition parsing and validation
-- ✅ Job registry for tracking installed workflows
-- ✅ Multi-platform support (Claude Code, Gemini, Copilot)
-- ✅ Jinja2-based skill file generation
-- ✅ Git integration for work branch management
-- ✅ CLI with `install` command
-- ✅ Core skills: `deepwork.define` and `deepwork.refine`
-
 ## Installation
 
 ### Prerequisites
@@ -46,27 +31,35 @@ deepwork install --platform claude  # or gemini, copilot
 
 This will:
 - Create `.deepwork/` directory structure
-- Initialize job registry
-- Generate core DeepWork skills
+- Generate core DeepWork jobs
+- Install DeepWork jobs for your AI assistant
+- Configure hooks for your AI assistant to enable policies
 
 ## Quick Start
 
-### 1. Define a Workflow
 
-Use Claude Code (or your AI assistant) to define a new job:
+
+### 1. Define a Job
+Jobs are multi-step workflows where each Step has clear input and output artifacts, making them easier to manage effectively.
+
+The process of defining a job itself is actually a DeepWork job. You can see it at `.deepwork/jobs/deepwork_jobs/`.
+
+To start the process, just run the first Step in the job:
 
 ```
-/deepwork.define
+/deepwork_jobs.define
 ```
 
 Follow the interactive prompts to:
-- Name your workflow
+- Name your job
 - Define steps with inputs/outputs
 - Specify dependencies between steps
 
+It will also prompt you to go on the the next Step in the job.
+
 ### 2. Execute Steps
 
-Run individual steps of your workflow:
+Run individual steps of your job:
 
 ```
 /your_job_name.step_1
@@ -83,7 +76,7 @@ The AI will:
 Use the refine skill to update existing jobs:
 
 ```
-/deepwork.refine
+/deepwork_jobs.refine
 ```
 
 ## Example: Competitive Research Workflow
@@ -215,9 +208,6 @@ ruff format src/
 ## Documentation
 
 - **[Architecture](doc/architecture.md)**: Complete design specification
-- **[Template Review](doc/TEMPLATE_REVIEW.md)**: Skill template documentation
-- **[Status](STATUS.md)**: Implementation progress
-- **[Next Steps](NEXT_STEPS.md)**: Future development roadmap
 
 ## Project Structure
 
@@ -227,7 +217,6 @@ deepwork/
 │   ├── cli/              # Command-line interface
 │   ├── core/             # Core functionality
 │   │   ├── parser.py     # Job definition parsing
-│   │   ├── registry.py   # Job registry management
 │   │   ├── detector.py   # Platform detection
 │   │   └── generator.py  # Skill file generation
 │   ├── templates/        # Jinja2 templates

diff --git a/claude.md b/claude.md
@@ -155,7 +155,7 @@ my-project/
 ## Key Files to Reference
 
 - `doc/architecture.md` - Comprehensive architecture documentation
-- `readme.md` - High-level project overview
+- `README.md` - High-level project overview
 - `shell.nix` - Development environment setup
 
 ## Development Guidelines
@@ -206,9 +206,3 @@ If a job exists in `src/deepwork/standard_jobs/`, it is a standard job and MUST
 3. **Performance**: Job import completes in <10 seconds
 4. **Extensibility**: New AI platforms can be added in <2 days
 5. **Quality**: 90%+ test coverage, zero critical bugs
-
-## Questions or Issues?
-
-- See `doc/architecture.md` for detailed design documentation
-- Check `readme.md` for high-level concepts
-- Reference implementation phases for current work focus